Three-Dimensional Convolutional Neural Network for Prostate MRI Segmentation and Comparison of Prostate Volume Measurements by Use of Artificial Neural Network and Ellipsoid Formula

Abstract

OBJECTIVE. The purposes of this study were to assess the performance of a 3D convolutional neural network (CNN) for automatic segmentation of prostates on MR images and to compare the volume estimates from the 3D CNN with those of the ellipsoid formula. MATERIALS AND METHODS. The study included 330 MR image sets that were divided into 260 training sets and 70 test sets for automated segmentation of the entire prostate. Among these, 162 training sets and 50 test sets were used for transition zone segmentation. Assisted by manual segmentation by two radiologists, the following values were obtained: estimates of ground-truth volume (V-GT), software-derived volume (V-SW), mean of V(GT )and V-SW (V-AV), and automatically generated volume from the 3D CNN (V-NET). These values were compared with the volume calculated with the ellipsoid formula (V-EL). RESULTS. The Dice similarity coefficient for the entire prostate was 87.12% and for the transition zone was 76.48%. There was no significant difference between V-NET and V-AV (p = 0.689) in the test sets of the entire prostate, whereas a significant difference was found between V-EL and V-AN (p < 0.001). No significant difference was found among the volume estimates in the test sets of the transition zone. Overall intraclass correlation coefficients between the volume estimates were excellent (0.887-0.995). In the test sets of entire prostate, the mean error between V-GT and V-NET (2.5) was smaller than that between V-GT and V-EL (3.3). CONCLUSION. The fully automated network studied provides reliable volume estimates of the entire prostate compared with those obtained with the ellipsoid formula. Fast and accurate volume measurement by use of the 3D CNN may help clinicians evaluate prostate disease.